Blockchain-Powered Secure and Scalable Threat Intelligence System With Graph Convolutional Autoencoder and Reinforcement Learning Feedback Loop
As the field of cybersecurity has experienced continual changes, up-to-date techniques have become increasingly necessary to analyze and defend against threats. Furthermore, the current methods consistently produce false alarms and sometimes completely miss real threats. This paper proposes an appro...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10870178/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823857175779344384 |
|---|---|
| author | Mohamad Khayat Ezedin Barka Mohamed Adel Serhani Farag Sallabi Khaled Shuaib Heba M. Khater |
| author_facet | Mohamad Khayat Ezedin Barka Mohamed Adel Serhani Farag Sallabi Khaled Shuaib Heba M. Khater |
| author_sort | Mohamad Khayat |
| collection | DOAJ |
| description | As the field of cybersecurity has experienced continual changes, up-to-date techniques have become increasingly necessary to analyze and defend against threats. Furthermore, the current methods consistently produce false alarms and sometimes completely miss real threats. This paper proposes an approach that integrates secure blockchain technology with data preprocessing, deep learning, and reinforcement learning to enhance threat detection and response capabilities. To secure the exchange of threat intelligence information, a safe blockchain network is used, which comprises Byzantine Fault Tolerance for high data integrity and Zero-Knowledge Proofs for access control. All relevant information is cleaned and standardized prior to analysis. Subsequently, graph convolutional neural networks with autoencoders are trained on large unlabeled sets of threat data to automatically label various types of threats, with the system employing fuzzy logic to rank and score possible threats. Furthermore, we implemented a feedback loop that incorporates reinforcement learning, thereby improving model performance over time according to guidance provided by cybersecurity specialists. The proposed system achieved high accuracy, precision, negative predictive value, and MCC, as well as notably low FPR and FNR values. The results establish that the proposed system is a reliable and effective measure for detecting cyberthreats. |
| format | Article |
| id | doaj-art-f8c8f1f864b04ea3b3ecfcbc0e75dde8 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-f8c8f1f864b04ea3b3ecfcbc0e75dde82025-02-12T00:02:50ZengIEEEIEEE Access2169-35362025-01-0113247362474810.1109/ACCESS.2025.353816010870178Blockchain-Powered Secure and Scalable Threat Intelligence System With Graph Convolutional Autoencoder and Reinforcement Learning Feedback LoopMohamad Khayat0https://orcid.org/0000-0002-1774-786XEzedin Barka1https://orcid.org/0000-0002-3995-7198Mohamed Adel Serhani2https://orcid.org/0000-0001-7001-3710Farag Sallabi3https://orcid.org/0000-0002-2887-5410Khaled Shuaib4https://orcid.org/0000-0003-1397-0420Heba M. Khater5https://orcid.org/0000-0002-6394-3482College of Information Technology, United Arab Emirates University, Al Ain, United Arab EmiratesCollege of Information Technology, United Arab Emirates University, Al Ain, United Arab EmiratesCollege of Computing and Informatics, University of Sharjah, Sharjah, United Arab EmiratesCollege of Information Technology, United Arab Emirates University, Al Ain, United Arab EmiratesCollege of Information Technology, United Arab Emirates University, Al Ain, United Arab EmiratesCollege of Information Technology, United Arab Emirates University, Al Ain, United Arab EmiratesAs the field of cybersecurity has experienced continual changes, up-to-date techniques have become increasingly necessary to analyze and defend against threats. Furthermore, the current methods consistently produce false alarms and sometimes completely miss real threats. This paper proposes an approach that integrates secure blockchain technology with data preprocessing, deep learning, and reinforcement learning to enhance threat detection and response capabilities. To secure the exchange of threat intelligence information, a safe blockchain network is used, which comprises Byzantine Fault Tolerance for high data integrity and Zero-Knowledge Proofs for access control. All relevant information is cleaned and standardized prior to analysis. Subsequently, graph convolutional neural networks with autoencoders are trained on large unlabeled sets of threat data to automatically label various types of threats, with the system employing fuzzy logic to rank and score possible threats. Furthermore, we implemented a feedback loop that incorporates reinforcement learning, thereby improving model performance over time according to guidance provided by cybersecurity specialists. The proposed system achieved high accuracy, precision, negative predictive value, and MCC, as well as notably low FPR and FNR values. The results establish that the proposed system is a reliable and effective measure for detecting cyberthreats.https://ieeexplore.ieee.org/document/10870178/Autoencoderblockchaincybersecurityhybrid optimizationreinforcement learning |
| spellingShingle | Mohamad Khayat Ezedin Barka Mohamed Adel Serhani Farag Sallabi Khaled Shuaib Heba M. Khater Blockchain-Powered Secure and Scalable Threat Intelligence System With Graph Convolutional Autoencoder and Reinforcement Learning Feedback Loop IEEE Access Autoencoder blockchain cybersecurity hybrid optimization reinforcement learning |
| title | Blockchain-Powered Secure and Scalable Threat Intelligence System With Graph Convolutional Autoencoder and Reinforcement Learning Feedback Loop |
| title_full | Blockchain-Powered Secure and Scalable Threat Intelligence System With Graph Convolutional Autoencoder and Reinforcement Learning Feedback Loop |
| title_fullStr | Blockchain-Powered Secure and Scalable Threat Intelligence System With Graph Convolutional Autoencoder and Reinforcement Learning Feedback Loop |
| title_full_unstemmed | Blockchain-Powered Secure and Scalable Threat Intelligence System With Graph Convolutional Autoencoder and Reinforcement Learning Feedback Loop |
| title_short | Blockchain-Powered Secure and Scalable Threat Intelligence System With Graph Convolutional Autoencoder and Reinforcement Learning Feedback Loop |
| title_sort | blockchain powered secure and scalable threat intelligence system with graph convolutional autoencoder and reinforcement learning feedback loop |
| topic | Autoencoder blockchain cybersecurity hybrid optimization reinforcement learning |
| url | https://ieeexplore.ieee.org/document/10870178/ |
| work_keys_str_mv | AT mohamadkhayat blockchainpoweredsecureandscalablethreatintelligencesystemwithgraphconvolutionalautoencoderandreinforcementlearningfeedbackloop AT ezedinbarka blockchainpoweredsecureandscalablethreatintelligencesystemwithgraphconvolutionalautoencoderandreinforcementlearningfeedbackloop AT mohamedadelserhani blockchainpoweredsecureandscalablethreatintelligencesystemwithgraphconvolutionalautoencoderandreinforcementlearningfeedbackloop AT faragsallabi blockchainpoweredsecureandscalablethreatintelligencesystemwithgraphconvolutionalautoencoderandreinforcementlearningfeedbackloop AT khaledshuaib blockchainpoweredsecureandscalablethreatintelligencesystemwithgraphconvolutionalautoencoderandreinforcementlearningfeedbackloop AT hebamkhater blockchainpoweredsecureandscalablethreatintelligencesystemwithgraphconvolutionalautoencoderandreinforcementlearningfeedbackloop |